Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces

被引:7
|
作者
Song, Yiying [1 ]
Qu, Yukun [2 ]
Xu, Shan [1 ]
Liu, Jia [3 ,4 ]
机构
[1] Beijing Normal Univ, Fac Psychol, Beijing Key Lab Appl Expt Psychol, Beijing, Peoples R China
[2] Beijing Normal Univ, State Key Lab Cognit Neurosci & Learning, Beijing, Peoples R China
[3] Tsinghua Univ, Dept Psychol, Beijing, Peoples R China
[4] Tsinghua Univ, Tsinghua Lab Brain & Intelligence, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
deep convolutional neural network; face recognition; reverse correlation analysis; face representation; visual intelligence; OBJECT; INFORMATION;
D O I
10.3389/fncom.2020.601314
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Deep convolutional neural networks (DCNN) nowadays can match human performance in challenging complex tasks, but it remains unknown whether DCNNs achieve human-like performance through human-like processes. Here we applied a reverse-correlation method to make explicit representations of DCNNs and humans when performing face gender classification. We found that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies. Importantly, the prior task experience, which the VGG-Face was pre-trained to process faces at the subordinate level (i.e., identification) as humans do, seemed necessary for such representational similarity, because AlexNet, a DCNN pre-trained to process objects at the basic level (i.e., categorization), succeeded in gender classification but relied on a completely different representation. In sum, although DCNNs and humans rely on different sets of hardware to process faces, they can use a similar and implementation-independent representation to achieve the same computation goal.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Modeling naturalistic face processing in humans with deep convolutional neural networks
    Guo Jiahui
    Ma Feilong
    Castello, Matteo Visconti di Oleggio
    Nastase, Samuel A.
    Haxby, James V.
    Gobbini, M. Ida
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2023, 120 (43)
  • [2] Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to Humans
    Zeman, Astrid
    Leers, Tim
    de Beeck, Hans Op
    JOURNAL OF COMPUTATIONAL NEUROSCIENCE, 2024, 52 : S99 - S100
  • [3] Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to Humans
    Zeman, Astrid
    Leers, Tim
    de Beeck, Hans Op
    JOURNAL OF COMPUTATIONAL NEUROSCIENCE, 2024, 52 : S99 - S100
  • [4] Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to Humans
    Zeman, Astrid
    Leers, Tim
    De Beeck, Hans Op
    PERCEPTION, 2022, 51 : 17 - 18
  • [5] Configural relations in humans and deep convolutional neural networks
    Baker, Nicholas
    Garrigan, Patrick
    Phillips, Austin
    Kellman, Philip J. J.
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2023, 5
  • [6] An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation
    Hoseini, Farnaz
    Shahbahrami, Asadollah
    Bayat, Peyman
    JOURNAL OF DIGITAL IMAGING, 2018, 31 (05) : 738 - 747
  • [7] An Efficient Implementation of Deep Convolutional Neural Networks on a Mobile Coprocessor
    Jin, Jonghoon
    Gokhale, Vinayak
    Dundar, Aysegul
    Krishnamurthy, Bharadwaj
    Martini, Berin
    Culurciello, Eugenio
    2014 IEEE 57TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2014, : 133 - 136
  • [8] An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation
    Farnaz Hoseini
    Asadollah Shahbahrami
    Peyman Bayat
    Journal of Digital Imaging, 2018, 31 : 738 - 747
  • [9] Deep Convolutional Neural Networks Implementation for the Analysis of Urine Culture
    Alouani, David J.
    Ransom, Eric M.
    Jani, Mehul
    Burnham, Carey-Ann
    Rhoads, Daniel D.
    Sadri, Navid
    CLINICAL CHEMISTRY, 2022, 68 (04) : 574 - 583
  • [10] Deep Convolutional Neural Networks for Chaos Identification in Signal Processing
    Makarenko, Andrey V.
    2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2018, : 1467 - 1471